# VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments

arXiv: https://arxiv.org/abs/2207.11810 · HTML: https://mlsanity.com/paper/2207.11810/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 24 Jul 2022.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation](https://mlsanity.com/paper/1907.12347/) (2019)
- [Captioning Images Taken by People Who Are Blind](https://mlsanity.com/paper/2002.08565/) (2020)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Grounding Answers for Visual Questions Asked by Visually Impaired People](https://mlsanity.com/paper/2202.01993/) (2022)
- [FGN: Fully Guided Network for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2003.13954/) (2020)
- [One-Shot Instance Segmentation](https://mlsanity.com/paper/1811.11507/) (2018)
- [Why Does a Visual Question Have Different Answers?](https://mlsanity.com/paper/1908.04342/) (2019)
- [ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition](https://mlsanity.com/paper/2104.03841/) (2021)
- [Assessing Image Quality Issues for Real-World Problems](https://mlsanity.com/paper/2003.12511/) (2020)
- [Vision Skills Needed to Answer Visual Questions](https://mlsanity.com/paper/2010.03160/) (2020)
- [FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter](https://mlsanity.com/paper/2104.00073/) (2021)
- [Few-Example Object Detection with Model Communication](https://mlsanity.com/paper/1706.08249/) (2017)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)](https://mlsanity.com/paper/1705.00366/) (2017)

## Built on by (most cited first, 11 of 11)

- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments](https://mlsanity.com/paper/2307.07757/) (2023)
- [Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment](https://mlsanity.com/paper/2304.14623/) (2023)
- [Acknowledging Focus Ambiguity in Visual Questions](https://mlsanity.com/paper/2501.02201/) (2025)
- [Vision as Unified Multimodal Generation](https://mlsanity.com/paper/2607.06560/) (2026)
- [BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2407.18243/) (2024)
- [Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn](https://mlsanity.com/paper/2305.07625/) (2023)
- [A Large Vision-Language Model based Environment Perception System for Visually Impaired People](https://mlsanity.com/paper/2504.18027/) (2025)
- [Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information](https://mlsanity.com/paper/2512.10102/) (2025)
- [Position: Assistive Agents Need Accessibility Alignment](https://mlsanity.com/paper/2605.13579/) (2026)
- [Time-Aware Assistive Navigation](https://mlsanity.com/paper/2609.05596/) (2026)

## Abstract (arXiv)

We introduce a few-shot localization dataset originating from photographers who authentically were trying to learn about the visual content in the images they took. It includes nearly 10,000 segmentations of 100 categories in over 4,500 images that were taken by people with visual impairments. Compared to existing few-shot object detection and instance segmentation datasets, our dataset is the first to locate holes in objects (e.g., found in 12.3% of our segmentations), it shows objects that occupy a much larger range of sizes relative to the images, and text is over five times more common in our objects (e.g., found in 22.4% of our segmentations). Analysis of three modern few-shot localization algorithms demonstrates that they generalize poorly to our new dataset. The algorithms commonly struggle to locate objects with holes, very small and very large objects, and objects lacking text. To encourage a larger community to work on these unsolved challenges, we publicly share our annotated few-shot dataset at https://vizwiz.org .